A gas migration law study of a large-scale 3D physical similarity simulation with an adaptive Kalman filter algorithm

Purpose In this study, a physical similarity simulation plays a significant role in the study of crack evolution and the gas migration mechanism. A sensor is deployed inside a comparable artificial rock formation to assure the accuracy of the experiment results. During the building of the simulated rock formation, a huge volume of acidic gas is released, causing numerous sensor measurement mistakes. Additionally, the gas concentration estimation approach is subject to uncertainty because of the complex rock formation environment. As a result, the purpose of this study is to introduce an adaptive Kalman filter approach to reduce observation noise, increase the accuracy of the gas concentration estimation model and, finally, determine the gas migration law. Design/methodology/approach First, based on the process of gas floatation-diffusion and seepage, the gas migration model is established according to Fick’s second law, and a simplified modeling method using diffusion flux instead of gas concentration is presented. Second, an adaptive Kalman filter algorithm is introduced to establish a gas concentration estimation model, taking into account the model uncertainty and the unknown measurement noise. Finally, according to a large-scale physical similarity simulation platform, a thorough experiment about gas migration is carried out to extract gas concentration variation data with certain ventilation techniques and to create a gas chart of the time-changing trend. Findings This approach is used to determine the changing process of gas distribution for a certain ventilation mode. The results match the rock fissure distribution condition derived from the microseismic monitoring data, proving the effectiveness of the approach. Originality/value For the first time in large-scale three-dimensional physical similarity simulations, the adaptive Kalman filter data processing method based on the inverse Wishart probability density function is used to solve the problem of an inaccurate process and measurement noise, laying the groundwork for studying the gas migration law and determining the gas migration mechanism.

A Transfer Learning Technique for Inland Chlorophyll-a Concentration Estimation Using Sentinel-3 Imagery

Chlorophyll-a (Chla) concentration, which serves as a phytoplankton substitute in inland waters, is one of the leading indicators for water quality. Generally, water samples are analyzed in professional laboratories, and Chla concentrations are measured regularly for the purpose of water quality monitoring. However, limited spatial water sampling and the labor-intensive nature of data collection make global and long-term monitoring difficult. The developments of remote-sensing optical sensors and technologies make the long-term monitoring of Chla concentrations for an entire water body more achievable. Many studies based on machine learning techniques, such as regression and artificial neural network (ANN) methods, have recently been proposed for Chla concentration estimation using optical satellite images. The methods based on machine learning can achieve accurate estimation. However, overfitting problems may arise because the in situ Chla dataset is generally insufficient to train a complicated machine learning model, which makes trained models inapplicable. In this study, an ANN model containing three convolutional and two fully connected layers with 4953 unknown parameters is designed. A transfer learning method, consisting of model pretraining, main-training, and fine-tuning stages, is proposed to ease the problem of insufficient in situ samples. In the model pretraining stage, the ANN model is pretrained and initialized using samples derived from an existing Chla concentration model. The pretrained ANN model is then fine-tuned using the proposed transfer learning technique with in situ samples collected in five different campaigns carried out during early 2019 from Laguna Lake, the Philippines. Before the transfer learning, data augmentation and rebalancing methods are conducted to enrich the variability and to near-uniformly distribute the in situ samples in Chla concentration space, respectively. To estimate the alleviation of model overfitting, the trained ANN model, using an in situ dataset from Laguna Lake, was tested using an in situ dataset from Lake Victoria, Uganda, obtained in 2019, which has a similar trophic state as Laguna Lake. The experimental results from Sentinel-3 imagery indicated that the overfitting problem was significantly alleviated and the trained ANN model outperformed related models in terms of the root-mean-squared error of the estimated Chla concentrations.

Effect of Dust Deposition on Chlorophyll Concentration Estimation in Urban Plants from Reflectance and Vegetation Indexes

Using reflectance spectroscopy to monitor vegetation pigments is a crucial method to know the nutritional status, environmental stress, and phenological phase of vegetation. Defining cities as targeted areas and common greening plants as research objects, the pigment concentrations and dust deposition amounts of the urban plants were classified to explore the spectral difference, respectively. Furthermore, according to different dust deposition levels, this study compared and discussed the prediction models of chlorophyll concentration by correlation analysis and linear regression analysis. The results showed: (1) Dust deposition had interference effects on pigment concentration, leaf reflectance, and their correlations. Dust was an essential factor that must be considered. (2) The influence of dust deposition on chlorophyll—a concentration estimation was related to the selected vegetation indexes. Different modeling indicators had different sensitivity to dust. The SR705 and CIrededge vegetation indexes based on the red edge band were more suitable for establishing chlorophyll-a prediction models. (3) The leaf chlorophyll concentration prediction can be achieved by using reflectance spectroscopy data. The effect of the chlorophyll estimation model under the levels of “Medium dust” and “Heavy dust” was worse than that of “Less dust”, which meant the accumulation of dust had interference to the estimation of chlorophyll concentration. The quantitative analysis of vegetation spectrum by reflectance spectroscopy shows excellent advantages in the research and application of vegetation remote sensing, which provides an important theoretical basis and technical support for the practical application of plant chlorophyll content prediction.

In-Cylinder Oxygen Concentration Estimation Based on Virtual Measurement and Data Fusion Algorithm for Turbocharged Diesel Engines

In-cylinder oxygen concentration (ICOC) is critical for advanced combustion control of internal combustion engines, and is hard to be accessed in commercial measurements. In existing research, ICOC is predicted by conventional dynamical model based on mass/energy conservation, which suffers from uncertainties such as inaccuracy of volumetric efficiency or the error of orifice geometry. In this paper, we enhance the ICOC estimation by implementing two vital strategies. Firstly, we introduce a method called virtual measurement to resist the conventional model uncertainties, in this method we modeling the ICOC as a function of ignition delay which can be obtained by measuring the in-cylinder pressure. Secondly, we apply Kalman filter to fuse the ICOC results from the conventional dynamical model and the virtual measurement. The data fusion algorithm turns the estimation to a predictor-corrector fashion, which further improves the overall accuracy and robustness. The proposed approach is validated through a calibrated GT-Power engine model. The results show that the estimation error can be achieved form at worst 0.03 to at best 0.01 on steady state.